market-brand
Warn
Audited by Snyk on Apr 18, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The SKILL.md Step 1 ("Gather Source Material") explicitly instructs the agent to fetch and analyze public web content (homepage, about, product pages, blog posts, social media profiles, email newsletters) using browser tools or analyze_page.py, meaning untrusted third‑party content is ingested and must be interpreted to drive analysis and generated outputs.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata